No abstract

With the burgeoning growth of the job market and a surge in applications, the processes of job recommendation and candidate selection have become complex and labor-intensive. The advent of new technologies such as machine learning has automated these processes, yet the unstructured nature of resumes, often in PDF format, necessitates laborious data extraction for efficient skill-based candidate screening and categorization. Ineffectual recruitment can result from mismatched skills. The system proposed in this study aims to address these challenges by automatically fetching and categorizing resumes, extracting critical information, and utilizing job descriptions for candidate selection and recommendations. Unstructured data from PDF documents is extracted using a PDF reader, and machine learning algorithms, specifically logistic regression and Gaussian Naï ve Bayes, are employed for generating recommendations. In an innovative approach, this system not only classifies resumes but also recommends updates or rewrites. Performance of the proposed system is evaluated in terms of classification accuracy and the effectiveness of update recommendations, and results are compared with alternative models. This research represents a significant advancement in the application of machine learning to the automation of job recommendation and candidate selection processes.